rf.blog (Page 7)

ADHD Diary No-Travel-Day Magatama Building Neurodivergent Security Personal Vision Open Source

ADHD Diary #005: When the Vision Finally Clicks

No-Travel-Day. The week Magatama stopped being a collection of security tools and became a platform. What happens inside an ADHD brain when 18 months of fragmented work suddenly makes sense.

Rene Fichtmueller / 2026-05-26 / ~2 min read

bgp looking-glass network-ops

Looking-Glass Output Is Not Reality — An Operator's Mental Model

A looking glass is a window. You stand on one side, look through, and see a slice of the network. The slice is real. It is also one router, at

Rene Fichtmueller / 2026-05-25 / ~3 min read

AI Security Open Source ShieldX ShieldY LLM Prompt Injection Security MITRE ATLAS Red Team TypeScript

The Open Source AI Security Stack That Actually Exists

Vendor solutions for LLM security cost $50,000/year and scan for yesterday's attacks. The open source stack is fragmented but works. Here's what actually exists — and what's still missing.

Rene Fichtmueller / 2026-05-23 / ~2 min read

dsp coherent vendor-consolidation

Coherent DSP Vendors Are Down to Three. Here's What That Means.

Six coherent DSP houses competed in the optical market in 2018. By 2020 the field was five. By 2022 it was four. As of mid-2025, three remain. Two of those

Rene Fichtmueller / 2026-05-22 / ~4 min read

Ollama Local LLM Mac Studio Production AI Self-Hosted Privacy llama qwen Apple Silicon AI Infrastructure

Ollama in Production: Running 70B Locally

Mac Studio M4 Pro with 48GB unified memory runs llama3.3:70b for reasoning tasks. Real latency numbers, model selection logic, and where local inference actually beats cloud.

Rene Fichtmueller / 2026-05-22 / ~2 min read

cpo packaging ai-fabric

Pluggable vs Embedded — When the CPO Hype Actually Pays Off

Every conference deck about co-packaged optics shows the same number: switching ASIC SerDes drives 30 to 40 percent of the system power, and CPO can eliminate most of it. The

Rene Fichtmueller / 2026-05-21 / ~3 min read

LLM Gateway AI Circuit Breaker Failover Production AI TypeScript Fastify Confidence Scoring Ollama Architecture

LLM Gateway Patterns: What We Learned After 50,000 Requests

Circuit breakers, confidence scoring, failover chains — an LLM gateway isn't a proxy. After 50,000 production requests through our internal gateway, here's what the patterns actually look like.

Rene Fichtmueller / 2026-05-21 / ~2 min read

otdr fiber-testing field-ops

OTDR Trace Reading: Three Mistakes Even Senior Field Techs Make

I've watched a fifteen-year fiber technician misread a ghost reflection as a real splice loss. He took the OTDR screen at face value, called the trace a bad

Rene Fichtmueller / 2026-05-20 / ~3 min read

RAG LLM Production AI Embeddings Vector Database Qdrant AI Engineering Chunking Retrieval OpenAI

Why Your RAG Pipeline Fails in Production

Tutorials show RAG working at 95% recall on toy datasets. Production systems hit 60%. The gap isn't the technology — it's three implementation choices that look harmless and aren't.

Rene Fichtmueller / 2026-05-20 / ~2 min read